Created
June 3, 2013 13:59
-
-
Save maowug/5698324 to your computer and use it in GitHub Desktop.
init django with tabelog data
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
#encoding: utf-8 | |
from django.conf import settings | |
from django.db.models import signals | |
from django.db import transaction | |
# | |
# from tbhBase import models as tbhBaseModels | |
# from tbhBase.models import Rst,Rvw | |
import os | |
import cPickle | |
from bs4 import BeautifulSoup | |
def init(sender, created_models=[], **kwargs): | |
""" | |
:param sender: | |
:param created_models: | |
:param kwargs: | |
""" | |
if tbhBaseModels.Rst in created_models: | |
# init_data_path = os.path.join(settings.SITE_ROOT,'data','東京_154_1_銀座_67_2_イ_67_.data') | |
for root, dirs, files in os.walk(os.path.join(settings.SITE_ROOT,'data')): | |
for fl in files: | |
if fl=='.DS_Store': | |
continue | |
init_data_path=os.path.join(root, fl) | |
print "importing data from: "+init_data_path | |
try: | |
rstList=cPickle.load(open(init_data_path,'rw')) | |
except: | |
print "------------------- unPickle: "+init_data_path | |
continue | |
for rst in rstList: | |
newRst=Rst() | |
for k in rst.keys(): | |
if k=='name': | |
newRst.name=rst[k].encode('utf-8') | |
elif k=='genre': | |
newRst.genre=rst[k].encode('utf-8') | |
elif k=='addr': | |
newRst.addr=rst[k].encode('utf-8') | |
elif k=='seat': | |
newRst.seat=rst[k].encode('utf-8') | |
elif k=='bgt': | |
newRst.bgt=rst[k].encode('utf-8') | |
elif k=='avg': | |
newRst.avg=rst[k].encode('utf-8') | |
elif k=='usage': | |
newRst.usage=rst[k].encode('utf-8') | |
elif k=='KWs': | |
newRst.KWs=','.join(rst[k]).encode('utf-8') | |
elif k=='rvwList': | |
newRst.save() | |
for rvw in rst[k]: | |
newRvw=Rvw() | |
newRvw.rst=newRst | |
newRvw.title=rvw['title'].encode('utf-8') | |
newRvw.profile=rvw['profile'].encode('utf-8') | |
newRvw.time=rvw['time'].encode('utf-8') | |
newRvw.prices=''.join(rvw['prices']).encode('utf-8') | |
newRvw.totalScore=str(rvw['totalScore']).encode('utf-8') | |
newRvw.scores=str(rvw['scores']).encode('utf-8') | |
newRvw.vote=str(rvw['vote']).encode('utf-8') | |
newRvw.situation=str(rvw['situation']).encode('utf-8') | |
# #comment todo:prettify | |
newRvw.comment=BeautifulSoup(rvw['comment'].encode('utf-8')).get_text() | |
newRvw.save() | |
pass | |
else: | |
pass | |
# print "sa39s" | |
#eof for-k in rst.keys() | |
newRst.save() | |
del rstList | |
signals.post_syncdb.connect(init, sender=tbhBaseModels) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment